GetLatentSize - ComfyUI Built-in Node Documentation - ComfyUI

Reads an image or video latent and returns its width, height, frame count, and batch size, so the geometry can be reused without decoding the latent. Use it to size noise masks, align resolutions, or work out overlaps when tiling a sampler. The measured values are also printed on the node itself.

Inputs

Parameter	Description	Data Type	Required	Range
`latent`	The image or video latent to inspect. When the latent holds several streams, the first one is measured.	LATENT	Yes	-

Outputs

Output Name	Description	Data Type
`width`	The width of the latent, in latent cells rather than pixels.	INT
`height`	The height of the latent, in latent cells rather than pixels.	INT
`frames`	The number of frames in the latent. Image latents have a single frame.	INT
`batch_size`	The number of latents in the batch.	INT

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): f75b3347cb1853b035b0bb283d5487ab1532d561d66d3cae3c67f54bf693d31a